TRST01 is a ClimateTech and Digital Trust Infrastructure company that builds AI-native platforms for traceability, sustainability, carbon markets, and compliance-driven supply chains. Leveraging Digital Public Infrastructure (DPI), AI, blockchain, geospatial intelligence, and data governance, TRST01 enables trusted, transparent, and interoperable ecosystems across agriculture, commodities, manufacturing, and environmental markets.
Its solutions include end-to-end traceability, EUDR compliance, digital MRV (dMRV), sovereign carbon registries, ESG reporting, and AI-powered decision support. TRST01 also developed the Open Agri Trace Stack (OATS), an open, standards-based blueprint for agricultural traceability.
TRST01 partners with governments, enterprises, and development institutions to build trusted, compliant, and sustainable digital ecosystems that deliver measurable climate and business impact.
Job Description: AI Engineer – Agent Orchestration & AI PlatformRole
Title- AI Engineer – Agent OrchestrationLocation
Remote / On-site as required
Employment TypeFull-time
Role Summary
We are looking for an experienced AI Engineer who can design, build, deploy, and manage a complete AI Agent Orchestration Layer for enterprise applications. The candidate will be responsible for developing multi-agent workflows, integrating LLMs with business systems, building retrieval-augmented generation pipelines, enabling tool-based AI agents, and deploying scalable AI services in cloud or on-premise environments.The role requires hands-on experience with LLMs, agent frameworks, workflow orchestration, APIs, vector databases, cloud infrastructure, and production-grade AI deployment practices.
Key Responsibilities
1. AI Agent Orchestration Design
- Design and implement end-to-end AI agent orchestration architecture.
- Build single-agent and multi-agent workflows for business use cases.
- Define agent roles, responsibilities, memory, tools, decision logic, and workflow states.
- Implement agentic workflows using frameworks such as LangGraph, LangChain, CrewAI, AutoGen, Semantic Kernel, or similar tools.
- Design human-in-the-loop workflows for approvals, review, escalation, and exception handling.
- Build reusable agent patterns for research, document processing, compliance checks, data validation, reporting, and customer support.
2. LLM Integration & Prompt Engineering
- Integrate large language models such as OpenAI GPT, Claude, Gemini, Llama, Mistral, Qwen, or other open-source models.
- Design and optimize prompts for accuracy, consistency, and business relevance.
- Implement system prompts, task prompts, tool-use prompts, guardrail prompts, and output formatting instructions.
- Evaluate model responses and improve prompt performance through testing and iteration.
- Support both cloud-hosted and self-hosted LLM deployments where required.
3. Retrieval-Augmented Generation
- Build RAG pipelines for enterprise knowledge search and document intelligence.
- Ingest, clean, chunk, embed, and index documents from PDFs, Word files, websites, databases, SharePoint, Google Drive, or internal systems.
- Work with vector databases such as Pinecone, Weaviate, Milvus, Chroma, Qdrant, FAISS, Azure AI Search, or PostgreSQL pgvector.
- Implement semantic search, hybrid search, metadata filtering, reranking, and context retrieval.
- Improve answer quality using grounding, citations, source traceability, and hallucination reduction techniques.
4. Workflow & Tool Integration
- Connect AI agents with enterprise tools, APIs, databases, dashboards, CRMs, ERPs, GIS systems, document systems, and cloud services.
- Build tool-calling capabilities for agents to perform actions such as data lookup, validation, report generation, ticket creation, email drafting, and system updates.
- Integrate orchestration engines such as Temporal, Airflow, Prefect, n8n, Apache Kafka, or event-driven workflows.
- Design API-based communication between AI agents and backend microservices.
- Implement secure access to external tools using OAuth, API keys, service accounts, and role-based access.
5. AI Platform Engineering
- Set up the complete AI orchestration platform from development to production.
- Design scalable backend services for AI workloads using Python, FastAPI, Flask, Node.js, or similar frameworks.
- Deploy AI services using Docker, Kubernetes, cloud services, or VM-based infrastructure.
- Configure model serving using Ollama, vLLM, TGI, KServe, Seldon, Ray Serve, or cloud-native model endpoints.
- Build reusable APIs for chat, document Q&A, summarization, classification, extraction, and autonomous workflows.
- Maintain proper environment separation for development, staging, and production.
6. Data Engineering for AI
- Build data pipelines for structured, semi-structured, and unstructured data.
- Work with SQL and NoSQL databases for AI application development.
- Prepare datasets for model evaluation, fine-tuning, embeddings, and analytics.
- Implement data validation, deduplication, metadata tagging, and document versioning.
- Support integration with data lakes, warehouses, and enterprise repositories.
7. Model Evaluation & Monitoring
- Create evaluation frameworks for agent accuracy, response quality, latency, cost, and reliability.
- Implement test cases for prompts, workflows, tools, and RAG pipelines.
- Track hallucinations, retrieval accuracy, tool execution success, and user feedback.
- Use observability tools for logging, tracing, monitoring, and debugging AI workflows.
- Monitor token usage, inference cost, response time, and system performance.
8. Security, Governance & Compliance
- Implement guardrails for responsible AI usage.
- Ensure secure handling of sensitive business data.
- Apply RBAC, audit logs, access control, data masking, and encryption where required.
- Design approval workflows for high-risk AI decisions.
- Ensure AI outputs are explainable, traceable, and aligned with business governance requirements.
- Support compliance with internal security policies and regulatory requirements.
9. Documentation & Team Collaboration
- Prepare technical architecture documents for AI agent systems.
- Document prompts, agent workflows, API integrations, deployment steps, and operational runbooks.
- Work closely with product managers, business teams, data engineers, backend developers, DevOps teams, and clients.
- Support demos, proof of concepts, pilot deployments, and production rollouts.
- Train internal teams on how to use and maintain AI agents.
Required Skills
- Strong hands-on experience with Python.
- Experience with LLMs and AI agent frameworks such as LangGraph, LangChain, CrewAI, AutoGen, or Semantic Kernel.
- Good understanding of AI agent architecture, tool calling, memory, planning, and workflow orchestration.
- Experience with RAG pipelines and vector databases.
- Strong knowledge of APIs, microservices, and backend development.
- Working knowledge of SQL databases and data processing.
- Experience with Docker and cloud or VM-based deployments.
- Understanding of prompt engineering and LLM evaluation.
- Ability to integrate AI systems with business applications and enterprise data sources.
- Good debugging, documentation, and problem-solving skills.
Preferred Skills
- Experience with Kubernetes and production AI deployments.
- Experience with Ollama, vLLM, Hugging Face Transformers, KServe, Seldon, or Ray Serve.
- Experience with cloud platforms such as AWS, Azure, or Google Cloud.
- Knowledge of workflow tools such as Temporal, Airflow, Prefect, or n8n.
- Experience with Kafka or event-driven architecture.
- Understanding of fine-tuning, LoRA, model quantization, and GPU-based inference.
- Experience with AI observability tools such as LangSmith, Arize, Phoenix, MLflow, OpenTelemetry, Prometheus, or Grafana.
- Knowledge of enterprise security, IAM, OAuth, RBAC, and audit logging.
- Experience in document intelligence, compliance automation, traceability, sustainability, agriculture, finance, or government platforms is an added advantage.
Technical Stack ExposureThe candidate should have experience or working knowledge in the following areas:
- Programming: Python, JavaScript/TypeScript
- AI Frameworks: LangGraph, LangChain, CrewAI, AutoGen, Semantic Kernel
- LLMs: GPT, Claude, Gemini, Llama, Mistral, Qwen, DeepSeek or similar
- Vector Databases: pgvector, Qdrant, Milvus, Weaviate, Pinecone, Chroma, FAISS
- Backend: FastAPI, Flask, Node.js, REST APIs, GraphQL
- Databases: PostgreSQL, MySQL, MongoDB, Redis
- Model Serving: Ollama, vLLM, Hugging Face TGI, KServe, Seldon, Ray Serve
- Workflow Tools: Temporal, Airflow, Prefect, n8n, Kafka
- DevOps: Docker, Kubernetes, GitHub Actions, CI/CD, Linux
- Cloud: AWS, Azure, GCP, private cloud, or VM-based infrastructure
- Monitoring: Prometheus, Grafana, OpenTelemetry, LangSmith, MLflow
Educational Qualification
- Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Data Science, Software Engineering, Information Technology, or a related field.
- Equivalent hands-on experience in AI engineering, backend engineering, or data platform development may also be considered.
Experience
- 3–6 years of experience in software engineering, AI engineering, data engineering, or platform engineering.
- Minimum 1–2 years of practical experience working with LLMs, RAG, AI agents, or AI workflow automation.
- Experience in building at least one production-grade AI application or enterprise AI proof of concept is preferred.
Key Deliverables
- Complete AI agent orchestration architecture.
- Working multi-agent workflow implementation.
- RAG-based enterprise knowledge system.
- APIs for AI agent interaction and backend integration.
- Secure deployment of AI services on cloud, VM, or Kubernetes.
- Monitoring, logging, and evaluation framework.
- Documentation for architecture, deployment, prompts, tools, and operations.
- Reusable agent templates for future business use cases.
Key Performance Indicators
- Successful deployment of AI agent workflows into production.
- Accuracy and reliability of AI responses and tool execution.
- Reduction in manual effort through AI automation.
- Response latency, uptime, and cost efficiency of AI services.
- Quality of documentation and maintainability of code.
- Successful integration with enterprise systems and databases.
- Compliance with security, governance, and audit requirements.
- Ability to quickly convert business requirements into working AI workflows.
Ideal Candidate ProfileThe ideal candidate is a hands-on AI engineer who can independently set up a complete AI orchestration layer, build intelligent agents, integrate them with enterprise systems, deploy them securely, and continuously improve their performance. The candidate should be comfortable working across AI, backend engineering, data pipelines and cloud infrastructure.
Pay: From ₹30,000.00 per month
Benefits:
- Health insurance
- Paid sick time
- Provident Fund
- Work from home
Work Location: Hybrid remote in Hyderabad, Telangana (Hyderabad, Hyderabad District)
